Loughborough University
Leicestershire, UK
LE11 3TU
+44 (0)1509 263171
Loughborough University

Loughborough University Institutional Repository

Please use this identifier to cite or link to this item: https://dspace.lboro.ac.uk/2134/17039

Title: Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios
Authors: Soltoggio, Andrea
Bullinaria, John A.
Mattiussi, Claudio
Durr, Peter
Floreano, Dario
Issue Date: 2008
Publisher: MIT Press
Citation: SOLTOGGIO, A. ... et al., 2008. Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios. IN: Artificial Life XI: Proceedings of the 11th International Conference on the Simulation and Synthesis of Living Systems (ALIFE 2008). MIT Press. pp. 569 - 576
Abstract: Neuromodulation is considered a key factor for learning and memory in biological neural networks. Similarly, artificial neural networks could benefit from modulatory dynamics when facing certain types of learning problem. Here we test this hypothesis by introducing modulatory neurons to enhance or dampen neural plasticity at target neural nodes. Simulated evolution is employed to design neural control networks for T-maze learning problems, using both standard and modulatory neurons. The results show that experiments where modulatory neurons are enabled achieve better learning in comparison to those where modulatory neurons are disabled. We conclude that modulatory neurons evolve autonomously in the proposed learning tasks, allowing for increased learning and memory capabilities.
Description: This is a conference paper.
Version: Accepted for publication
URI: https://dspace.lboro.ac.uk/2134/17039
ISBN: 9780262750172
Appears in Collections:Conference Papers and Presentations (Computer Science)

Files associated with this item:

File Description SizeFormat
SoltoggioBullinariaMattiussiDuerrFloreano2008.pdfAccepted version433.55 kBAdobe PDFView/Open


SFX Query

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.